Personalized Question Answering

نویسنده

  • Silvia Quarteroni
چکیده

A common problem in Question Answering – and Information Retrieval in general – is information overload, i.e. an excessive amount of data from which to search for relevant information. This results in the risk of high recall but low precision of the information returned to the user. In turn, this affects the relevance of answers with respect to the users’ needs, as queries can be ambiguous and even answers extracted from documents with relevant content may be ill-received by users if they are too difficult (or simple) for them. We address the issue by integrating a User Modelling component to personalize the results of a Web-based opendomain Question Answering system based on the user’s reading level and interests. RÉSUMÉ. Un problème commun aux systèmes de Question-Réponse, et de recherche documentaire plus généralement, est la présence d’une quantité excessive de données parmi lesquelles chercher l’information pertinente. Ceci apporte un rappel élevé mais se traduit par un risque de faible précision de l’information retournée à l’utilisateur. De plus, ce problème concerne la pertinence des réponses vis-à-vis des besoins des utilisateurs, puisque les questions peuvent être ambiguës et même des réponses extraites de documents au contenu pertinent peuvent être mal reçues si elles sont trop compliquées (ou trop simples) pour les utilisateurs. Nous adressons ce problème en incorporant une composante de modélisation de l’utilisateur afin de personnaliser les résultats d’un système Web de Question-Réponse à domaine ouvert sur la base de son niveau de lecture et de ses interêts.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Personalized Question Answering: A Use Case for Business Analysis

In this paper, we introduce the Personalized Question Answering framework, which aims at addressing certain limitations of existing domain specific Question Answering systems. Current development efforts are ongoing to apply this framework to a use case within the domain of Business Analysis, highlighting the important role of domain specific semantics. Current research indicates that the inclu...

متن کامل

Personalized, Interactive Question Answering on the Web

Two of the current issues of Question Answering (QA) systems are the lack of personalization to the individual users’ needs, and the lack of interactivity by which at the end of each Q/A session the context of interaction is lost. We address these issues by designing and implementing a model of personalized, interactive QA based on a User Modelling component and on a conversational interface. O...

متن کامل

Using a User-Interactive QA System for Personalized E-Learning

A personalized e-learning framework based on a user-interactive question-answering (QA) system is proposed, in which a user-modeling approach is used to capture personal information of students and a personalized answer extraction algorithm is proposed for personalized automatic answering. In our approach, a topic ontology (or concept hierarchy) of course content defined by an instructor is use...

متن کامل

User Modelling for Personalized Question Answering

In this paper, we address the problem of personalization in question answering (QA). We describe the personalization component of YourQA, our web-based QA system, which creates individual models of users based on their reading level and interests. First, we explain how user models are dynamically created, saved and updated to filter and re-rank the answers. Then, we focus on how the user’s inte...

متن کامل

Personalized Semantic Search based Intelligent Question Answering System using Semantic Web and Domain Ontology

This paper proposed the architecture of question answering system for a specific domain using semantic web andontology. It defines the question answering system using semantic searching methodology and natural language processing techniques. The traversal in ontology is based upon conceptual graph matching type. The repositories are the collection of documents which hold the information related...

متن کامل

ارایه یک پیکره‌ پرسش و پاسخ مذهبی در زبان فارسی

Question answering system is a field in natural language processing and information retrieval noticed by researchers in these decades. Due to a growing interest in this field of research, the need to have appropriate data sources is perceived. Most researches about developing question answering corpus area have been done in English so far, but in other languages as Persian, the lack of these co...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • TAL

دوره 51  شماره 

صفحات  -

تاریخ انتشار 2010